Change detection (CD) from remote sensing images has been widely used in land management and urban planning. Benefiting from deep learning, numerous methods have achieved significant results in the CD of clearly changed targets. However, there are still significant challenges in the CD of weak targets, such as targets with small size, targets with blurred boundaries, and targets with low distinguishability from the background. Feature extraction from these targets can result in the loss of critical spatial features, potentially leading to decreased CD performance. Inspired by the improvement of multi-scale features for CD of weak target, a hierarchical feature interaction network with multi-scale fusion (HFIFNet) was proposed. Firstly, a hierarchical feature interactive fusion module (HFIFM) is proposed, which achieves optimized multi-channel feature interaction and enhances the distinguishability between weak targets and background. Moreover, the module also achieves cross scale feature fusion, which compensates for the loss of spatial feature of changed targets at a single scale during feature extraction. Secondly, VMamba Block (VMB) is utilized to obtain global features, and a spatial feature localization module (SFLM) was proposed to enhance the saliency of spatial features such as edges and textures. The distinguishability between weak targets and irrelevant spatial features is further enhanced. Our method has been experimentally evaluated on three public datasets, and outperformed state-of-the-art approaches by 1.06%, 1.41% and 2.63% in F1 score on the LEVIR-CD, S2Looking, and NALand datasets, respectively. These results affirm the effectiveness of our method for weak targets in CD tasks.

Detecting objects in remote sensing images is essential for intelligent interpretation. Although deep neural networks have made significant progress in recent years, they often struggle with complex backgrounds in remote sensing images, which can lead to inaccurate detection. To tackle this problem, a self-supervised adaptive fusion network (SSAFN) has been developed. The SSAFN includes an adaptive fusion module (AFM) and a self-supervised task module (SSTM). The AFM mainly fuses the deep semantic information to the shallow features with appropriate weights to enhance the semantic information of the shallow features. The SSTM is mainly to constrain the AFM through self-supervised tasks to fulfill the function similar to the attention mechanism: to make the AFM enhance the target feature representation and suppress the background information. The SSAFN reduces the impact of complex backgrounds on object representation, resulting in better detection results for various types of objects such as buildings, ships and more. The proposed method has been tested on various datasets and has not only improved the detection accuracy for different types of objects but also enhanced the performance of popular object detection algorithms.

Building detection from panchromatic (PAN) and Multi-spectral (MS) images is an essential task for many practical applications. In this paper, a dual-stream asymmetric fusion network is proposed, named DAFNet. DAFNet can achieve effective information fusion at the feature level. It obtains better building detection performance from three perspectives: 1) A two-stream network structure is designed to guarantee the ability to extract information from PAN and MS images; 2) An asymmetric feature fusion (AFF) module is proposed to fuse features efficiently and concisely; 3) Two consistency regularization losses, i.e., PAN information preservation (PiP) loss and cross-modal semantic consistency (CSC) loss are applied to further explore the consistency between features for better fusion. The experiments are conducted on a challenging building detection dataset collected from GaoFen-2 satellite images. Comprehensive evaluations on 12 popular detection methods demonstrate the superiority of our DAFNet compared with the existing state-of-the-art fusion methods. We reveal that feature-level fusion is more suitable for building detection from PAN-MS images. Code is released at https://github.com/floatingstarZ/DAFNet

Change detection (CD) from multi-temporal remote sensing (RS) images plays a crucial role in various fields. Motivated by the advancements in deep learning within computer vision, numerous deep learning-based methodologies have been proposed for CD. However, the intricate backgrounds inherent in RS images present challenges to CD algorithms, leaving a notable disparity from practical applications. The changed regions between RS images frequently related to salient targets, yet encoding modules tend to forfeit the spatial information of these targets and disregard their spatial correlations during feature interaction. Consequently, leveraging the spatial correlation among targets emerges as a pivotal concern for CD algorithms. In this paper, a multi-stage spatial attention network with mixed feature interaction (MAMI-CD) is proposed, which introduces two novel modules, i.e., a multi-stage attention module (MAM) and a mixed feature interaction module (MIM). The MAM extracts spatial attention features from encoding stages and transfers them to the decoding stages, thereby preserving the spatial information of targets while mitigating the influence of background noise. The MIM employs a channel-wise feature interaction instead of the traditional direct concatenation operation, enhancing the correlations between targets. MAMI-CD has been experimentally evaluated on three public datasets. On the LEVIR-CD, S2Looking and CDD datasets, our method outperformed the state-of-the-art by 0.65%, 0.93%, and 3.16% F1 score, respectively, thus affirming the beneficial impacts of spatial correlations in CD tasks. The code is now available at https://github.com/Han-MZ/MAMI-CD .